Miniature circuit breaker fault analysis method based on probabilistic neural network

A technology of probabilistic neural network and fault analysis method, applied in the direction of biological neural network model, neural learning method, circuit breaker test, etc., can solve the problems that the fault is not easy to find, cannot indicate the type of fault, and cannot accurately find the fault point, etc.

Inactive Publication Date: 2020-08-18
山东卓文信息科技有限公司
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the miniature circuit breaker itself fails, it can only be judged manually by disassembling the machine, and the fault point cannot be accurately found, and some faults are not easy to find, and are often misjudged as normal
GEWISS has developed an intelligent leakage circuit breaker with self-diagnosis function, but there are only three states, namely normal, warning and maintenance, and cannot indicate the type of fault

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Miniature circuit breaker fault analysis method based on probabilistic neural network
  • Miniature circuit breaker fault analysis method based on probabilistic neural network
  • Miniature circuit breaker fault analysis method based on probabilistic neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0092] A method for fault analysis of small circuit breakers based on probabilistic neural network, such as figure 2 shown, including the following steps: .

[0093] (1) Construct a probabilistic neural network model;

[0094] Such as figure 1 As shown, the probabilistic neural network model includes an input layer, a pattern layer, a summation layer, and an output layer connected in sequence; the input layer is used to input samples, and the number of neurons is equal to the feature dimension of the sample; the pattern layer is used to calculate the output probability, that is The output result of the probabilistic neural network model is the probability of a certain type of failure. The summation layer is used to obtain the sum of the output of the model layer nodes corresponding to the same category of test samples. The number of nodes is equal to the number of categories of samples; the output layer is used to The output of the above summation layer is normalized to obt...

Embodiment 2

[0109] According to a kind of probabilistic neural network-based fault analysis method for small circuit breakers described in Embodiment 1, the difference is that:

[0110] The pattern layer uses non-linear operations instead of sigmoid functions As an activation function, Zi is the radial basis function operation symbol, Zi=Xω, X is a sample, and ω is a weighting coefficient;

[0111] The probability Φ of the output of the jth neuron of the i-th class in the pattern layer ij (X) as shown in formula (I):

[0112]

[0113] In formula (I), p is the dimension of the training sample, that is, the required correlation dimension, σ is the smoothing factor, and X ij is the j-th hidden center vector of the i-th category, and X is the phase space vector of the input signal;

[0114] The probability density function f of the i-th category i As shown in formula (II):

[0115]

[0116] In formula (Ⅱ), L i is the number of training samples for category i.

[0117] In step (2...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a miniature circuit breaker fault analysis method based on a probabilistic neural network. The method comprises the following steps: (1) constructing a probabilistic neural network model; the system comprises an input layer, a mode layer, a summation layer and an output layer; (2) training and testing a probabilistic neural network model; respectively simulating each groupof vibration signals of the miniature circuit breaker under N fault types, carrying out classic modal decomposition on each group of vibration signals, and extracting a fourth-order intrinsic mode function IMF component; calculating the correlation dimension of the original signal and a fourth-order intrinsic mode function IMF component by using a G _ P algorithm; and (3) outputting a test resultthrough the trained probabilistic neural network model in the step (2). The probabilistic neural network is simple in learning process and high in training speed; classification is more accurate, andit can be guaranteed that the optimal solution under the Bayesian criterion is obtained; fault tolerance is good, and training data is allowed to be increased or decreased without long-time training.

Description

technical field [0001] The invention relates to the technical field of power system maintenance, in particular to a small circuit breaker fault analysis method based on a probabilistic neural network. Background technique [0002] As a terminal power distribution appliance, the miniature circuit breaker is an important part of the power grid, and is directly related to the safety of personal and property. Its good operating status is a necessary prerequisite to ensure the safety of users' electricity consumption. Therefore, the research on fault analysis of miniature circuit breakers has very important research significance and value. [0003] As a terminal power distribution appliance, the miniature circuit breaker is an important part of the power grid, and is directly related to the safety of personal and property. Its good operating status is a necessary prerequisite to ensure the safety of users' electricity consumption. Therefore, the research on fault analysis of min...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/00G06Q50/06G06N3/04G06N3/08G01R31/327G01H17/00
CPCG06Q10/20G06Q50/06G06N3/08G01R31/327G01H17/00G06N3/047
Inventor 徐通通陈浩
Owner 山东卓文信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap